This is Python Tutorial

This is my first python programm. Just started here.

print("Hello World")

Hello World

$a=b+c$

Variables and operator

x=3

%whos

Variable   Type    Data/Info
----------------------------
x          int     3

print(type(x))

<class 'int'>

abcd=55.6

%whos

Variable   Type     Data/Info
-----------------------------
abcd       float    55.6
x          int      3

a,b,c,d=1,3.4,"helow",-4

%whos

Variable   Type     Data/Info
-----------------------------
a          int      1
abcd       float    55.6
b          float    3.4
c          str      helow
d          int      -4
x          int      3

del abcd

print(abcd)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_5724/224357748.py in <module>
----> 1 print(abcd)

NameError: name 'abcd' is not defined

c=2+4j

type(c)

complex

%whos

Variable   Type       Data/Info
-------------------------------
a          int        1
b          float      3.4
c          complex    (2+4j)
d          int        -4
x          int        3

sumOfaAndb=a+b

print(sumOfaAndb)

4.4

print(type(sumOfaAndb))

<class 'float'>

3**2

9

3*2

6

8/2

4.0

8//2

4

-

  File "C:\Users\sayadur\AppData\Local\Temp/ipykernel_5724/476313318.py", line 1
    -
     ^
SyntaxError: invalid syntax

_

4

Comparison

print(2<3)

True

c=2<3
print(type(c))
print(c)

<class 'bool'>
True

print((not(2!=3) and True) or (False and True))

False

print((not(2!=3) and True) or (False and True))

False

print((not(2!=3) and False) or (False and True))

False

round(467.67)

468

G=divmod(34,9)

type(G)

tuple

print(G)

(3, 7)

G[0]

3

G[1]

7

34/9

3.7777777777777777

34//9

3

34%9

7

print(isinstance(1,int))

True

l=isinstance(1,int)

print(type(l))

<class 'bool'>

isinstance(1.1,int)

False

isinstance(1.1,(float,int))

True

pow(2,4)

16

2**4

16

pow(2,4,7)

2

pow(2,4,8)

0

pow(3,4)

81

pow(3,4,8)

1

a=input("Enter a number:")

Enter a number:56

type(a)

str

a=int(a)

type(a)

int

x=int(input("Enter a number:"))

Enter a number:45

type(x)

int

pow?

help(input)

Help on method raw_input in module ipykernel.kernelbase:

raw_input(prompt='') method of ipykernel.ipkernel.IPythonKernel instance
    Forward raw_input to frontends
    
    Raises
    ------
    StdinNotImplementedError if active frontend doesn't support stdin.

Control Flow

a=int(input())
b=int(input())
if a>b :
    print("a is greater than b")

3
2
a is greater than b

a=int(input())
b=int(input())
if a>b :
    print(a)
else:
    print(b)

4
5
5

a=int(input())
b=int(input())
if a>b :
    print(a)
else:
    print(b)

  File "C:\Users\sayadur\AppData\Local\Temp/ipykernel_8848/4258849755.py", line 5
    else:
    ^
SyntaxError: invalid syntax

a=int(input())
b=int(input())
if a>b :
    print("a is greate than b")
elif a==b:
    print("a equal to b")    
else:
    print("b is greate than a")

29
29
a equal to b

a=int(input())
b=int(input())
if a>b :
    print("a is greate than b")
elif a==b:
    print("a equal to b")    
else:
    print("b is greate than a")

34
56
b is greate than a

a=int(input("Enter Number"))
if a>10 :
    print("Your Number is above 10")
    if a>20:
        print("and also above 20")   
    else:
        print("but not above 20")
else:
    print("Your Number is below 10")
        
        

Enter Number1
Your Number is below 10

# Single line comments
"""
Muliti line Comments
Multilines Comments
"""

'\nMuliti line Comments\nMultilines Comments\n'

# Single line comments

"""
user will enter a floating input number let say 238.915. your
task is to find out the interger portion before the point (in this case)
and then check if that integer portion is even or odd  number ?
"""
x=float(input("Enter a real  number:"))
y=round(x)
if x>0:   
    if y>x:
        intPortion=y-1 
    else:    
        intPortion=y
        #print(intPortion)
else:
    if y<x:
        intPortion=y+1 
    else:    
        intPortion=y
if intPortion%2==0:    
    print("Even") 
else:    
    print("Odd")    
    

Enter a real  number:98.98
Even

#Control flow (loops)
n=int(input("Maximum Iteration number:"))
i=1
while i<n:
    if i%2==0:        
        print(i)
    else:
        pass
    i += 1
print("Done")    

Maximum Iteration number:10
2
4
6
8
Done

#Control flow (loops: break and continue)
n=int(input("Maximum Iteration number:"))
i=1
while True:
    if i%9==0:
        print("Break")
        break
    else:
        i += 1
        print("Continue")
        continue
    print("I am inside the loop")    
print("Done") 

Maximum Iteration number:10
Continue
Continue
Continue
Continue
Continue
Continue
Continue
Continue
Break
Done

L=[]
type(L)

list

L=[]
for i in range(10):
    print(i+1)
    L.append(i**2)

1
2
3
4
5
6
7
8
9
10

L

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

print(L)

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

L=[]
for i in range(10):
    print(i+1)
    L.append(i**2)
print(L)

1
2
3
4
5
6
7
8
9
10
[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

S={"apple",4.9,"cherry"}
type(S)

set

S={"apple",4.9,"cherry"}
i=0
for x in S:
    print(x)
    i=i+1
    if i==3:
        break
    else:
        pass
else:
    print("Loop is completed")

4.9
cherry
apple

#Control flow (Exploring a dictionary)
D={"A":10,"B":-19,"C":"abc"}
for x in D:
    print(x,D[x])
    

A 10
B -19
C abc

"""Given a list of number i.e. [1,2,3,4,-5,7,6,7,8]
that contains all the iterms in stored order from min to max. your
resutl will be another list [-5,1,2,3,4,5,6,7,8]
"""
L=[1,2,4,-5,7,6,9,3,2]
for j in range(len(L)):
    m=L[j]
    idx=j
    c=j
    for i in range(j,len(L)):
        if L[i]<m:
            m=L[i]
            idx=c
        c+=1 
    tmp=L[j]
    L[j]=m
    L[idx]=tmp
print(L)        

[-5, 1, 2, 2, 3, 4, 6, 7, 9]

Function

def printSuccess():
    print("I am done")
    print("Send me another task")

    

printSuccess()

I am done
Send me another task

printSuccess()

I am done
Send me another task

def printSuccess2():
    """this function does nothing"""   
    print("Send me another task")

len??

help(printSuccess)

Help on function printSuccess in module __main__:

printSuccess()

help(printSuccess2)

Help on function printSuccess2 in module __main__:

printSuccess2()
    this function does nothing

def printSuccess3(msg):
    """Function with argument"""   
    if isinstance(msg,str):
        print(msg)
    else:
        print("Your argument is not a sting")
        print("Here is the type what you have supplied ",msg)

printSuccess3("Test")

Test

printSuccess3(123)

Your argument is not a sting
Here is the type what you have supplied  123

printSuccess3?

y="helow world"
printSuccess3(y)

helow world

def mypow(a,b):
    """ This function compute poer just like builtin pow"""
    c=a**b
    print(c)

mypow(2,3)

8

def myAdd(a,b):
    c =a+b
    return c

myAdd(2,32)

34

d=myAdd(2,32)
print(d)

34

variableOUtsideFunstion=3

def g():
    print(variableOUtsideFunstion)

g()

3

myAdd(c)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_14092/2497071577.py in <module>
----> 1 myAdd(c)

TypeError: myAdd() missing 1 required positional argument: 'b'

def r():
    a=5
    b=4
    c=a+b
    d="something"
    return a,b,c,d

x,y,z,n=r()

print(x,y,z,n)

5 4 9 something

print(d)

34

print(n)

something

def myAddUniversal(*arg):
    s=0
    for i in range(len(arg)):
        s+=arg[i]
    return s

myAddUniversal(2,3,4,5,6)

20

def printAllVariableNameAndValues(**args):
    for x in args:
        print("variable Nameis:",x,"And Values is:",args[x])

printAllVariableNameAndValues(a=3,b="B",c="CCCC",y=10.7)

variable Nameis: a And Values is: 3
variable Nameis: b And Values is: B
variable Nameis: c And Values is: CCCC
variable Nameis: y And Values is: 10.7

Modules

import sys
sys.path.append('D:/sayadur/Data Science/mypythonmodules/')

import my_universal_functions as myfs

myfs.myAddUniversal??

c=myfs.myAddUniversal(2,4,5,7,-7,20)

print(c)

31

import sys
sys.path.append('D:/sayadur/Data Science/mypythonmodules/')
import my_universal_functions as myfs
c=myfs.myAddUniversal(2,4,5,7,-7,20)
print(c)

31

import sys
sys.path.append('D:/sayadur/Data Science/mypythonmodules/')
import my_universal_functions as myfs
c=myfs.myAddUniversal(2,4,5,7,-7,20)
vMyvalue=1234
d=myfs.checIfNotNumeric(vMyvalue)
print(c)
print(d)
print(myfs.myName)

31
True
Python Course

Practice

"""Given a list of number i.e. [1,2,3,4,-5,7,6,7,8]
that contains all the iterms in stored order from min to max. your
resutl will be another list [-5,1,2,3,4,5,6,7,8]
"""
def findAscendingNo(L):
    sys.path.append('D:/sayadur/Data Science/mypythonmodules/')
    import my_universal_functions as myfs
    v=0
   
    for p in range(0,len(L)):        
        if myfs.checIfNotNumeric(L[p])==True:            
            x=L[p]            
            v+=1 
            z=x
        else:
            pass
    return z
        
    """for j in range(len(z)):
        m=z[j]
        idx=j
        c=j
        for i in range(j,len(z)):
            if z[i]<m:
                m=z[i]
                idx=c
            c+=1 
        tmp=z[j]
        z[j]=m
        z[idx]=tmp"""
       #return(z) 

    

print(findAscendingNo([2,3,4,1,-6,8]))

8

print(findAscendingNo([2,3,4,1,-6,8,"hhhh"]))

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_14092/1088141836.py in <module>
----> 1 print(findAscendingNo([2,3,4,1,-6,8,"hhhh"]))

~\AppData\Local\Temp/ipykernel_14092/994433222.py in findAscendingNo(L)
     12             x=L[p]
     13             v+=1
---> 14             return X
     15             #Z[v]=x
     16         else:

NameError: name 'X' is not defined

import sys
sys.path.append('D:/sayadur/Data Science/mypythonmodules/')

import my_universal_functions as myfs

checIfNotNumeric?

Object `checIfNotNumeric` not found.

myfs.checIfNotNumeric??

def checIfNotNumeric(L):    
    for x in L:
        if not(isinstance(x,(int,float))):
            return False
        return True 

print(checIfNotNumeric([1,2,3]))

True

def checIfNotNumeric(L):    
    for x in L:
        if not(isinstance(x,(int,float))):
            return False
    return True 

def myAddUniversal(*args):
    s=0
    for i in range(len(args)):
        s+=args[i]
    return s
myName="Python Course"

"""Given a list of number i.e. ["a",2,3,4,1,-6,7,"hsdjfh"]
that contains all the iterms in stored order from min to max. your
resutl will be another list [-6, 1, 2, 3, 4, 7]
"""
def findAscendingNo(L):
    sys.path.append('D:/sayadur/Data Science/mypythonmodules/')
    import my_universal_functions as myfs
    v=0
    z=[]
   
    for p in range(len(L)):        
        if myfs.checIfNotNumeric(L[p])==True:            
            z.append(L[p])
        else:            
            pass
   
        
    for j in range(len(z)):
        m=z[j]
        idx=j
        c=j
        for i in range(j,len(z)):
            if z[i]<m:
                m=z[i]
                idx=c
            c+=1 
        tmp=z[j]
        z[j]=m
        z[idx]=tmp
    return(z) 

print(findAscendingNo(["a",2,3,4,"kjsgdkjdf",1,-6,7,"hsdjfh"]))

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_1532/3154888157.py in <module>
----> 1 print(findAscendingNo(["a",2,3,4,"kjsgdkjdf",1,-6,7,"hsdjfh"]))

~\AppData\Local\Temp/ipykernel_1532/3023806591.py in findAscendingNo(L)
      4 """
      5 def findAscendingNo(L):
----> 6     sys.path.append('D:/sayadur/Data Science/mypythonmodules/')
      7     import my_universal_functions as myfs
      8     v=0

NameError: name 'sys' is not defined

list1 = ['b','o','o','m']
list2 = ['r','e','d']

n = 2
new_list = []
for i in range(n): # append list1 until insert point
    new_list.append(list1[i])
for i in list2: # append all of list2
    new_list.append(i)
for i in range(n, len(list1)): # append the remainder of list1
    new_list.append(list1[i])

print(new_list)

['b', 'o', 'r', 'e', 'd', 'o', 'm']

String

s="python is good language"
t='It good for data science'

print(s)

python is good language

print(t)

It good for data science

print(s+t)

python is good languageIt good for data science

a="""python is good language.
     It good for data science """

print(a)

python is good language
asjdgkajsd 

print(a+s)

python is good language.
     It good for data science python is good language

Indexing and Slicing

s="pyt5on is good language"
print(s[3:8])
print(len(s))
print(s[3])
type(s[3])

5on i
23
5

str

#Example of slicing
s="pyt5on is good language"
print(s[-8:-3])
print(s[-3:-1])

langu
ag

s="""pyt5on is good language
        Sayadur Rahaman"""
print(len(s))
print(s[-8:-3])
print(s[-3:-1])

47
 Raha
ma

s[0:12:2]

'pto sg'

a="    A Lot of Space at the     beGinning and end     "

a

'    A Lot of Space at the     beGinning and end     '

b=a.strip()

b

'A Lot of Space at the     beGinning and end'

print(b.lower())

a lot of space at the     beginning and end

print(b.upper())

A LOT OF SPACE AT THE     BEGINNING AND END

print(a.replace(" ",""))

ALotofSpaceatthebeGinningandend

print(a.replace(" ",""))

ALotofSpaceatthebeGinningandend

a="abc;def;hgyuiio;123"
L=a.split(";")
print(L)

['abc', 'def', 'hgyuiio', '123']

L[0]

'abc'

a.capitalize()

'Abc;def;hgyuiio;123'

c="hsgdj jhasgjdhas jhasgjdh"

print(c.capitalize())

Hsgdj jhasgjdhas jhasgjdh

c="hsgdj jhasgjdhas jhasgjdh"

c.capitalize()

'Hsgdj jhasgjdhas jhasgjdh'

print("at" in "asdfaatdea")

True

"bxc"<"aef"

False

print("we are learning \"string\" here")

we are learning "string" here

print('we are learning "string" here')

we are learning "string" here

print('we are \t learning  here')

we are 	 learning  here

print('we are \n learning  here')

we are 
 learning  here

print("c:\name\drive")

c:
ame\drive

print(r"c:\name\drive")

c:\name\drive

"Data Structure"

Data Structure

L = [1,2,3,4.9,"name",3] #list
T = (1,2,3,4.9,"name",3)  #Tuple
S = {1,2,3,4.9,"name",3} #Set
D = {23:"twothree",'B':43,'C':'CCD'} #Dictionary

print("The Type of L is",type(L))
print("The Type of T is",type(T))
print("The Type of S is",type(S))
print("The Type of D is",type(D))

The Type of L is <class 'list'>
The Type of T is <class 'tuple'>
The Type of S is <class 'set'>
The Type of D is <class 'dict'>

print(D)

{23: 'twothree', 'B': 43, 'C': 'CCD'}

print(D[23])

twothree

print(L[1])

2

print(L[1])
print(T[1])
print(3 in S)
print(D[23])

2
2
True
twothree

print(D['C'])

CCD

S

{1, 2, 3, 4.9, 'name'}

L

[1, 2, 3, 4.9, 'name', 3]

D

{23: 'twothree', 'B': 43, 'C': 'CCD'}

S

{1, 2, 3, 4.9, 'name'}

L[1:3]

[2, 3]

L[::-1]

[3, 'name', 4.9, 3, 2, 1]

L

[1, 2, 3, 4.9, 'name', 3]

T[:3]

(1, 2, 3)

L=L+["Game"]

L

[1, 2, 3, 4.9, 'name', 3, 'Game']

S.add("Game")

S

{1, 2, 3, 4.9, 'Game', 'name'}

S.remove("Game")

S

{1, 2, 3, 4.9, 'name'}

L.append(6.7)

L

[1, 2, 3, 4.9, 'name', 3, 'Game', 6.7]

T2 =('a','b')

T+T2

(1, 2, 3, 4.9, 'name', 3, 'a', 'b')

D['newkey']="Sayadur"

D

{23: 'twothree', 'B': 43, 'C': 'CCD', 'newkey': 'Sayadur'}

D2= {"y":"YYY",'z':"ZZZZ"}

D+D2

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_18504/3903222224.py in <module>
----> 1 D+D2

TypeError: unsupported operand type(s) for +: 'dict' and 'dict'

D.update(D2)

D

{23: 'twothree',
 'B': 43,
 'C': 'CCD',
 'newkey': 'Sayadur',
 'y': 'YYY',
 'z': 'ZZZZ'}

L.pop?

L.pop

<function list.pop(index=-1, /)>

L.pop(1)

'name'

L

[1, 3]

T

(1, 2, 3, 4.9, 'name', 3)

D

{23: 'twothree', 'B': 43, 'C': 'CCD'}

S

{1, 2, 3, 4.9, 'name'}

L = [1,2,3,4.9,"name",3]

L

[1, 2, 3, 4.9, 'name', 3]

D2={'A':L,'B':T,'C':S,'D':D} #Here L=List,T=Tuple,S=Set,D=Dictinary

D2['A']

[1, 2, 3, 4.9, 'name', 3]

D2['D']

{23: 'twothree', 'B': 43, 'C': 'CCD'}

D2['A'][3]

4.9

K = D2['D']

K

{23: 'twothree', 'B': 43, 'C': 'CCD'}

for x in K:
    print(x,K[x])

23 twothree
B 43
C CCD

for x in K:
    print(K[x])

twothree
43
CCD

L3=[L,T,S,D,"New data"]

L3

[[1, 2, 3, 4.9, 'name', 3],
 (1, 2, 3, 4.9, 'name', 3),
 {1, 2, 3, 4.9, 'name'},
 {23: 'twothree', 'B': 43, 'C': 'CCD'},
 'New data']

type(L3[-1])

str

type(L3[0])

list

type(L3[1])

tuple

type(L3[2])

set

type(L3[3])

dict

L3=[x**2 for x in range(10)]

L3

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

S3={x**2 for x in range(12)}

S3

{0, 1, 4, 9, 16, 25, 36, 49, 64, 81, 100, 121}

t={x**2 for x in range(12)}

t

{0, 1, 4, 9, 16, 25, 36, 49, 64, 81, 100, 121}

type(t)

set

"""Let say you are teacher and you have different
student record containing of a student id, and marks list in
each subject where different student have taken duffernt
number of subects. All these records are in hard copy. you want to enter all the
data in computer and to compute the average marks of each student and display
"""
def getDataFromUser():
    D={}
    while True:
        studentID=input("Enter Student ID:")
        marksList=input("Enter the marks by comma separated values:")
        moreStudents=input('Enter "no" to quite insertion:')
        if studentID in D:
            print(studentID,"is already inserted")
        else:
            D[studentID]=marksList.split(",")
        if moreStudents.lower()=="no":
            return D               
                           
            

studentData=getDataFromUser()

Enter Student ID:1
Enter the marks by comma separated values:80,56,89,87,98
Enter "no" to quite insertion:jhd
Enter Student ID:2
Enter the marks by comma separated values:87,67,99,98,56
Enter "no" to quite insertion:hgkhgk
Enter Student ID:3
Enter the marks by comma separated values:65,76,99,99,90
Enter "no" to quite insertion:ty
Enter Student ID:3
Enter the marks by comma separated values:78,47,78,56,54
Enter "no" to quite insertion:gg
3 is already inserted
Enter Student ID:4
Enter the marks by comma separated values:65,90,56,34,98
Enter "no" to quite insertion:no

studentData

{'1': ['80', '56', '89', '87', '98'],
 '2': ['87', '67', '99', '98', '56'],
 '3': ['65', '76', '99', '99', '90'],
 '4': ['65', '90', '56', '34', '98']}

def getAvgMarks(D):
    avgMarks={}
    for x in D:
        L=D[x]
        s=0
        for marks in L:
            s += int(marks)
        avgMarks[x]=s/len(L)
    return avgMarks    

avgM=getAvgMarks(studentData)

for x in avgM:
    print("Student :",x," got avg marks as:",avgM[x])

Student : 1  got avg marks as: 82.0
Student : 2  got avg marks as: 81.4
Student : 3  got avg marks as: 85.8
Student : 4  got avg marks as: 68.6

Numpy

import numpy as np
a= np.array([1,2,3,5,7,8])
b= np.array(("Sayadur","Rahaman","Ashik"))
print(a)
print(b)

[1 2 3 5 7 8]
['Sayadur' 'Rahaman' 'Ashik']

type(b)

numpy.ndarray

Numpy(Dimensions)

# 2 dimenion Array
import numpy as np
a=np.array([[1,2,3,5,7,8],[21,22,33,55,77,88],[11,32,31,51,71,81]])
print(a.ndim)

2

# 3 dimenion Array
import numpy as np
b=np.array([[[1,2,3,5,7,8],[21,22,33,55,77,88]],[[100,200,300,500,700,800],[210,220,330,550,770,880]]])
print(b.ndim)

3

# 1 dimenion Array
import numpy as np
c= np.array([1,2,3,5,7,8])
print(c.ndim)

1

b[1,0,2]

300

b[0,0,2]

3

b[0,1,4]

77

b[1,1,5]

880

print(b.shape[0],b.shape[1],b.shape[2])

2 2 6

print(b.shape)

(2, 2, 6)

print(a.shape)

(3, 6)

print(c.shape)

(6,)

c.size

6

b.size

24

b.nbytes

96

print(b)

[[[  1   2   3   5   7   8]
  [ 21  22  33  55  77  88]]

 [[100 200 300 500 700 800]
  [210 220 330 550 770 880]]]

A=np.arange(100)

A

array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
       34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
       51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67,
       68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84,
       85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99])

A=np.arange(20,100)

A

array([20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36,
       37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53,
       54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70,
       71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87,
       88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99])

A=np.arange(20,100,3) 
# for i in range(20,100,3) means start from 20 increment by 3 upto 100

A

array([20, 23, 26, 29, 32, 35, 38, 41, 44, 47, 50, 53, 56, 59, 62, 65, 68,
       71, 74, 77, 80, 83, 86, 89, 92, 95, 98])

print(range(10))

range(0, 10)

print(list(range(10)))

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]

A=np.random.permutation(np.arange(10))

A

array([3, 8, 5, 9, 1, 6, 0, 2, 4, 7])

np.random.randint

<function RandomState.randint>

v=np.random.randint(20,300)

v

220

type(v)

int

import matplotlib.pyplot as plt
plt.hist(np.random.rand(1000),bins=100)

(array([10.,  8., 10., 13.,  8., 11.,  9., 10., 15., 13., 12.,  4.,  7.,
        11., 11., 12., 16.,  8., 12.,  6., 10.,  7., 10., 12.,  6., 13.,
        14.,  7.,  8.,  3., 12., 14., 13., 13.,  7., 12.,  8., 13., 14.,
        10., 11.,  7.,  7., 16.,  8., 15.,  9.,  9.,  7., 10., 11.,  8.,
        11.,  8., 12., 11., 14., 12.,  9.,  6., 15., 10.,  3., 11., 11.,
        15.,  7.,  8.,  8., 10.,  9., 17.,  6., 11.,  9.,  4.,  6., 11.,
        14.,  3.,  9., 10., 11., 11.,  8., 12., 11., 10., 11., 10., 10.,
        11.,  8.,  9., 11.,  9., 10., 10., 11.,  7.]),
 array([8.99344888e-05, 1.00869381e-02, 2.00839418e-02, 3.00809454e-02,
        4.00779490e-02, 5.00749527e-02, 6.00719563e-02, 7.00689599e-02,
        8.00659636e-02, 9.00629672e-02, 1.00059971e-01, 1.10056974e-01,
        1.20053978e-01, 1.30050982e-01, 1.40047985e-01, 1.50044989e-01,
        1.60041993e-01, 1.70038996e-01, 1.80036000e-01, 1.90033004e-01,
        2.00030007e-01, 2.10027011e-01, 2.20024014e-01, 2.30021018e-01,
        2.40018022e-01, 2.50015025e-01, 2.60012029e-01, 2.70009033e-01,
        2.80006036e-01, 2.90003040e-01, 3.00000044e-01, 3.09997047e-01,
        3.19994051e-01, 3.29991055e-01, 3.39988058e-01, 3.49985062e-01,
        3.59982065e-01, 3.69979069e-01, 3.79976073e-01, 3.89973076e-01,
        3.99970080e-01, 4.09967084e-01, 4.19964087e-01, 4.29961091e-01,
        4.39958095e-01, 4.49955098e-01, 4.59952102e-01, 4.69949105e-01,
        4.79946109e-01, 4.89943113e-01, 4.99940116e-01, 5.09937120e-01,
        5.19934124e-01, 5.29931127e-01, 5.39928131e-01, 5.49925135e-01,
        5.59922138e-01, 5.69919142e-01, 5.79916145e-01, 5.89913149e-01,
        5.99910153e-01, 6.09907156e-01, 6.19904160e-01, 6.29901164e-01,
        6.39898167e-01, 6.49895171e-01, 6.59892175e-01, 6.69889178e-01,
        6.79886182e-01, 6.89883185e-01, 6.99880189e-01, 7.09877193e-01,
        7.19874196e-01, 7.29871200e-01, 7.39868204e-01, 7.49865207e-01,
        7.59862211e-01, 7.69859215e-01, 7.79856218e-01, 7.89853222e-01,
        7.99850225e-01, 8.09847229e-01, 8.19844233e-01, 8.29841236e-01,
        8.39838240e-01, 8.49835244e-01, 8.59832247e-01, 8.69829251e-01,
        8.79826255e-01, 8.89823258e-01, 8.99820262e-01, 9.09817265e-01,
        9.19814269e-01, 9.29811273e-01, 9.39808276e-01, 9.49805280e-01,
        9.59802284e-01, 9.69799287e-01, 9.79796291e-01, 9.89793295e-01,
        9.99790298e-01]),
 <BarContainer object of 100 artists>)

B=np.random.randn(100000)
plt.hist(B,bins=200)

(array([1.000e+00, 1.000e+00, 1.000e+00, 1.000e+00, 1.000e+00, 2.000e+00,
        1.000e+00, 1.000e+00, 1.000e+00, 5.000e+00, 2.000e+00, 9.000e+00,
        7.000e+00, 4.000e+00, 5.000e+00, 9.000e+00, 6.000e+00, 1.100e+01,
        1.200e+01, 1.100e+01, 9.000e+00, 1.600e+01, 2.400e+01, 2.300e+01,
        1.800e+01, 2.100e+01, 2.800e+01, 3.600e+01, 3.400e+01, 4.900e+01,
        5.100e+01, 5.800e+01, 5.100e+01, 5.800e+01, 6.000e+01, 7.300e+01,
        8.000e+01, 1.080e+02, 1.120e+02, 1.150e+02, 1.110e+02, 1.250e+02,
        1.440e+02, 1.860e+02, 1.910e+02, 2.080e+02, 2.170e+02, 2.370e+02,
        2.600e+02, 2.760e+02, 3.250e+02, 3.660e+02, 3.750e+02, 4.140e+02,
        4.090e+02, 4.630e+02, 4.800e+02, 5.540e+02, 5.840e+02, 5.300e+02,
        6.150e+02, 6.460e+02, 7.090e+02, 6.990e+02, 7.930e+02, 8.090e+02,
        8.130e+02, 8.710e+02, 9.180e+02, 9.780e+02, 1.034e+03, 1.100e+03,
        1.148e+03, 1.169e+03, 1.203e+03, 1.229e+03, 1.289e+03, 1.307e+03,
        1.402e+03, 1.397e+03, 1.412e+03, 1.482e+03, 1.492e+03, 1.478e+03,
        1.566e+03, 1.622e+03, 1.550e+03, 1.565e+03, 1.592e+03, 1.680e+03,
        1.629e+03, 1.636e+03, 1.690e+03, 1.659e+03, 1.634e+03, 1.546e+03,
        1.670e+03, 1.654e+03, 1.648e+03, 1.623e+03, 1.588e+03, 1.590e+03,
        1.546e+03, 1.542e+03, 1.527e+03, 1.469e+03, 1.501e+03, 1.489e+03,
        1.377e+03, 1.374e+03, 1.339e+03, 1.341e+03, 1.293e+03, 1.205e+03,
        1.149e+03, 1.173e+03, 1.063e+03, 1.060e+03, 9.790e+02, 9.710e+02,
        9.380e+02, 8.720e+02, 8.110e+02, 8.380e+02, 7.030e+02, 7.320e+02,
        6.840e+02, 6.540e+02, 6.210e+02, 5.450e+02, 5.320e+02, 5.230e+02,
        4.440e+02, 3.930e+02, 3.930e+02, 3.340e+02, 2.990e+02, 3.120e+02,
        3.050e+02, 2.730e+02, 2.370e+02, 2.370e+02, 1.970e+02, 1.760e+02,
        1.850e+02, 1.720e+02, 1.430e+02, 1.430e+02, 1.340e+02, 1.330e+02,
        1.040e+02, 8.700e+01, 9.500e+01, 6.100e+01, 6.100e+01, 7.200e+01,
        5.400e+01, 4.800e+01, 5.700e+01, 3.300e+01, 2.900e+01, 3.100e+01,
        3.100e+01, 1.900e+01, 1.800e+01, 2.100e+01, 1.800e+01, 1.800e+01,
        9.000e+00, 1.200e+01, 1.200e+01, 3.000e+00, 9.000e+00, 4.000e+00,
        2.000e+00, 4.000e+00, 6.000e+00, 1.000e+00, 1.000e+00, 4.000e+00,
        2.000e+00, 1.000e+00, 1.000e+00, 1.000e+00, 1.000e+00, 0.000e+00,
        1.000e+00, 1.000e+00, 0.000e+00, 1.000e+00, 0.000e+00, 0.000e+00,
        0.000e+00, 0.000e+00, 0.000e+00, 0.000e+00, 0.000e+00, 0.000e+00,
        0.000e+00, 1.000e+00]),
 array([-3.96872333, -3.92661213, -3.88450092, -3.84238972, -3.80027851,
        -3.75816731, -3.7160561 , -3.6739449 , -3.63183369, -3.58972249,
        -3.54761129, -3.50550008, -3.46338888, -3.42127767, -3.37916647,
        -3.33705526, -3.29494406, -3.25283286, -3.21072165, -3.16861045,
        -3.12649924, -3.08438804, -3.04227683, -3.00016563, -2.95805442,
        -2.91594322, -2.87383202, -2.83172081, -2.78960961, -2.7474984 ,
        -2.7053872 , -2.66327599, -2.62116479, -2.57905359, -2.53694238,
        -2.49483118, -2.45271997, -2.41060877, -2.36849756, -2.32638636,
        -2.28427515, -2.24216395, -2.20005275, -2.15794154, -2.11583034,
        -2.07371913, -2.03160793, -1.98949672, -1.94738552, -1.90527432,
        -1.86316311, -1.82105191, -1.7789407 , -1.7368295 , -1.69471829,
        -1.65260709, -1.61049588, -1.56838468, -1.52627348, -1.48416227,
        -1.44205107, -1.39993986, -1.35782866, -1.31571745, -1.27360625,
        -1.23149505, -1.18938384, -1.14727264, -1.10516143, -1.06305023,
        -1.02093902, -0.97882782, -0.93671661, -0.89460541, -0.85249421,
        -0.810383  , -0.7682718 , -0.72616059, -0.68404939, -0.64193818,
        -0.59982698, -0.55771577, -0.51560457, -0.47349337, -0.43138216,
        -0.38927096, -0.34715975, -0.30504855, -0.26293734, -0.22082614,
        -0.17871494, -0.13660373, -0.09449253, -0.05238132, -0.01027012,
         0.03184109,  0.07395229,  0.1160635 ,  0.1581747 ,  0.2002859 ,
         0.24239711,  0.28450831,  0.32661952,  0.36873072,  0.41084193,
         0.45295313,  0.49506433,  0.53717554,  0.57928674,  0.62139795,
         0.66350915,  0.70562036,  0.74773156,  0.78984277,  0.83195397,
         0.87406517,  0.91617638,  0.95828758,  1.00039879,  1.04250999,
         1.0846212 ,  1.1267324 ,  1.1688436 ,  1.21095481,  1.25306601,
         1.29517722,  1.33728842,  1.37939963,  1.42151083,  1.46362204,
         1.50573324,  1.54784444,  1.58995565,  1.63206685,  1.67417806,
         1.71628926,  1.75840047,  1.80051167,  1.84262287,  1.88473408,
         1.92684528,  1.96895649,  2.01106769,  2.0531789 ,  2.0952901 ,
         2.13740131,  2.17951251,  2.22162371,  2.26373492,  2.30584612,
         2.34795733,  2.39006853,  2.43217974,  2.47429094,  2.51640215,
         2.55851335,  2.60062455,  2.64273576,  2.68484696,  2.72695817,
         2.76906937,  2.81118058,  2.85329178,  2.89540298,  2.93751419,
         2.97962539,  3.0217366 ,  3.0638478 ,  3.10595901,  3.14807021,
         3.19018142,  3.23229262,  3.27440382,  3.31651503,  3.35862623,
         3.40073744,  3.44284864,  3.48495985,  3.52707105,  3.56918225,
         3.61129346,  3.65340466,  3.69551587,  3.73762707,  3.77973828,
         3.82184948,  3.86396069,  3.90607189,  3.94818309,  3.9902943 ,
         4.0324055 ,  4.07451671,  4.11662791,  4.15873912,  4.20085032,
         4.24296152,  4.28507273,  4.32718393,  4.36929514,  4.41140634,
         4.45351755]),
 <BarContainer object of 200 artists>)

C=np.random.rand(2,3)

C

array([[0.25008488, 0.343122  , 0.92420939],
       [0.95734876, 0.14536173, 0.5476824 ]])

C.ndim

2

D=np.arange(100).reshape(4,25)

D.shape

(4, 25)

Numpy(Slicing) A[start:end:step]

import numpy np

  File "C:\Users\sayadur\AppData\Local\Temp/ipykernel_10272/1904197115.py", line 1
    import numpy np
                 ^
SyntaxError: invalid syntax

import numpy as np

A=np.arange(100)

B=A[3:10]
print(B)

[3 4 5 6 7 8 9]

B[0]=-1200

B

array([-1200,     4,     5,     6,     7,     8,     9])

A

array([    0,     1,     2, -1200,     4,     5,     6,     7,     8,
           9,    10,    11,    12,    13,    14,    15,    16,    17,
          18,    19,    20,    21,    22,    23,    24,    25,    26,
          27,    28,    29,    30,    31,    32,    33,    34,    35,
          36,    37,    38,    39,    40,    41,    42,    43,    44,
          45,    46,    47,    48,    49,    50,    51,    52,    53,
          54,    55,    56,    57,    58,    59,    60,    61,    62,
          63,    64,    65,    66,    67,    68,    69,    70,    71,
          72,    73,    74,    75,    76,    77,    78,    79,    80,
          81,    82,    83,    84,    85,    86,    87,    88,    89,
          90,    91,    92,    93,    94,    95,    96,    97,    98,
          99])

B=A[3:10].copy()

B

array([-1200,     4,     5,     6,     7,     8,     9])

A

array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
       34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
       51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67,
       68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84,
       85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99])

A[::5]

array([ 0,  5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80,
       85, 90, 95])

A[::-5]

array([99, 94, 89, 84, 79, 74, 69, 64, 59, 54, 49, 44, 39, 34, 29, 24, 19,
       14,  9,  4])

B=(A==-1200)*np.arange(A.size)

B

array([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])

idx=np.argwhere(A==-1200)[0][0]

idx

3

A[idx]=3

A

array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
       34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
       51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67,
       68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84,
       85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99])

A=np.round(10*np.random.rand(5,4))

A

array([[4., 9., 6., 4.],
       [6., 6., 8., 2.],
       [3., 4., 9., 5.],
       [8., 6., 9., 3.],
       [3., 9., 1., 6.]])

A[0:1]

array([[4., 9., 6., 4.]])

A[0,2]

6.0

A[1,:]

array([6., 6., 8., 2.])

A[0:2,1:0]

array([], shape=(2, 0), dtype=float64)

import numpy.linalg as la
la.inv(np.random.rand(3,3))

array([[ 2.60045808,  0.71864656, -2.60411358],
       [-0.59663354,  1.57415212, -0.61556338],
       [ 0.11676209, -1.10323528,  1.79250884]])

A.sort(axis=1)

A

array([[1., 2., 3., 4.],
       [3., 3., 6., 6.],
       [4., 4., 6., 8.],
       [5., 6., 9., 9.],
       [6., 8., 9., 9.]])

Numpy(More Indexing)

A=np.arange(100)

B=A[[3,5,6]]

B

array([3, 5, 6])

B=A[A<40]

B

array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
       34, 35, 36, 37, 38, 39])

B=A[(A<40) & (A>30)]

B

array([31, 32, 33, 34, 35, 36, 37, 38, 39])

Numpy(Broadcasting)

import numpy as np
A= np.round(10*np.random.rand(2,3))

A

array([[7., 1., 5.],
       [1., 9., 8.]])

A+(np.arange(2).reshape(2,1))

array([[ 7.,  1.,  5.],
       [ 2., 10.,  9.]])

B=np.round(10*np.random.rand(2,2))

B

array([[ 1.,  8.],
       [ 0., 10.]])

C=np.hstack((A,B))

C

array([[ 7.,  1.,  5.,  1.,  8.],
       [ 1.,  9.,  8.,  0., 10.]])

A=np.random.permutation(np.arange(10))

A.sort()

A

array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

np.sort(A)

array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

A=A[::-1]

A

array([9, 8, 7, 6, 5, 4, 3, 2, 1, 0])

A=np.array(["abc","howare you",'u765','e13'])

A.sort()

A

array(['abc', 'e13', 'howare you', 'u765'], dtype='<U10')

Numpy(Seed: ufuncs)

B=np.random.rand(1000000)
%timeit sum(B)
%timeit np.sum(B)

50.8 ms ± 545 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
367 µs ± 4.88 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

def mySum(G):
    s=0
    for x in G:
        s+=x
    return s

%timeit mySum(B)

65 ms ± 1.64 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

Pandas

import pandas as pd

print(pd.__version__)

1.3.4

A= pd.Series([2,3,4,5],index=['a','b','c','d'])

A.values

array([2, 3, 4, 5], dtype=int64)

type(A.values)

numpy.ndarray

type(A)

pandas.core.series.Series

A.index

Index(['a', 'b', 'c', 'd'], dtype='object')

A['a']

2

A['a':'c']

a    2
b    3
c    4
dtype: int64

grade_dict={'A':4,'A-':3.5,'B':3,'B-':2.5,'C':2}
grade=pd.Series(grade_dict)

grade.values

array([4. , 3.5, 3. , 2.5, 2. ])

marks_dict={'A':85,'A-':80,'B':75,'B-':70,'C':60}

marks=pd.Series(marks_dict)

marks.values

array([85, 80, 75, 70, 60], dtype=int64)

marks

A     85
A-    80
B     75
B-    70
C     60
dtype: int64

marks[0:2]

A     85
A-    80
dtype: int64

grade

A     4.0
A-    3.5
B     3.0
B-    2.5
C     2.0
dtype: float64

D=pd.DataFrame({'Grade':grade,'Marks':marks})

D.T

	A	A-	B	B-	C
Grade	4.0	3.5	3.0	2.5	2.0
Marks	85.0	80.0	75.0	70.0	60.0

D

	Grade	Marks
A	4.0	85
A-	3.5	80
B	3.0	75
B-	2.5	70
C	2.0	60

D.values

array([[ 4. , 85. ],
       [ 3.5, 80. ],
       [ 3. , 75. ],
       [ 2.5, 70. ],
       [ 2. , 60. ]])

D.values[2,0]

3.0

D.T

	A	A-	B	B-	C
Grade	4.0	3.5	3.0	2.5	2.0
Marks	85.0	80.0	75.0	70.0	60.0

D.values[2,0]

3.0

D['ScaledMarks']=100*(D['Marks']/90)

D

	Grade	Marks	ScaledMarks
A	4.0	85	94.444444
A-	3.5	80	88.888889
B	3.0	75	83.333333
B-	2.5	70	77.777778
C	2.0	60	66.666667

del D['ScaledMarks']

D

	Grade	Marks
A	4.0	85
A-	3.5	80
B	3.0	75
B-	2.5	70
C	2.0	60

G=D[D['Marks']>70]

G

	Grade	Marks
A	4.0	85
A-	3.5	80
B	3.0	75

A= pd.DataFrame([{'a':1,'b':4},{'a':-1,'c':-4},{'d':-5,'c':-7}])

A

	a	b	c	d
0	1.0	4.0	NaN	NaN
1	-1.0	NaN	-4.0	NaN
2	NaN	NaN	-7.0	-5.0

A.fillna(0)

	a	b	c	d
0	1.0	4.0	0.0	0.0
1	-1.0	0.0	-4.0	0.0
2	0.0	0.0	-7.0	-5.0

A.dropna?

Pandas (Indexing) loc and iloc

A= pd.Series(['a','b','c','d'],index=[1,3,5,7])

A

1    a
3    b
5    c
7    d
dtype: object

A[1:3]

3    b
5    c
dtype: object

A.loc[1:3]

1    a
3    b
dtype: object

A.iloc[1:3]

3    b
5    c
dtype: object

D

	Grade	Marks
A	4.0	85
A-	3.5	80
B	3.0	75
B-	2.5	70
C	2.0	60

D.iloc[2,:]

Grade     3.0
Marks    75.0
Name: B, dtype: float64

D.iloc[::-1,:]

	Grade	Marks
C	2.0	60
B-	2.5	70
B	3.0	75
A-	3.5	80
A	4.0	85

D

	Grade	Marks
A	4.0	85
A-	3.5	80
B	3.0	75
B-	2.5	70
C	2.0	60

Pandas (CSV Files)

import pandas as pd
import numpy as np
from sklearn.impute import SimpleImputer
df =pd.read_csv('D:\sayadur\Data Science\covid_19_data\covid_19_data.csv')

df.drop(['Sno','Last Update'],axis=1,inplace=True)

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_492/1737931629.py in <module>
----> 1 df.drop(['Sno','Last Update'],axis=1,inplace=True)

~\Anaconda3\lib\site-packages\pandas\util\_decorators.py in wrapper(*args, **kwargs)
    309                     stacklevel=stacklevel,
    310                 )
--> 311             return func(*args, **kwargs)
    312 
    313         return wrapper

~\Anaconda3\lib\site-packages\pandas\core\frame.py in drop(self, labels, axis, index, columns, level, inplace, errors)
   4904                 weight  1.0     0.8
   4905         """
-> 4906         return super().drop(
   4907             labels=labels,
   4908             axis=axis,

~\Anaconda3\lib\site-packages\pandas\core\generic.py in drop(self, labels, axis, index, columns, level, inplace, errors)
   4148         for axis, labels in axes.items():
   4149             if labels is not None:
-> 4150                 obj = obj._drop_axis(labels, axis, level=level, errors=errors)
   4151 
   4152         if inplace:

~\Anaconda3\lib\site-packages\pandas\core\generic.py in _drop_axis(self, labels, axis, level, errors)
   4183                 new_axis = axis.drop(labels, level=level, errors=errors)
   4184             else:
-> 4185                 new_axis = axis.drop(labels, errors=errors)
   4186             result = self.reindex(**{axis_name: new_axis})
   4187 

~\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in drop(self, labels, errors)
   6015         if mask.any():
   6016             if errors != "ignore":
-> 6017                 raise KeyError(f"{labels[mask]} not found in axis")
   6018             indexer = indexer[~mask]
   6019         return self.delete(indexer)

KeyError: "['Sno'] not found in axis"

df

	SNo	ObservationDate	Province/State	Country/Region	Last Update	Confirmed	Deaths	Recovered
0	1	1/22/2020	Anhui	Mainland China	1/22/2020 17:00	1	0	0
1	2	1/22/2020	Beijing	Mainland China	1/22/2020 17:00	14	0	0
2	3	1/22/2020	Chongqing	Mainland China	1/22/2020 17:00	6	0	0
3	4	1/22/2020	Fujian	Mainland China	1/22/2020 17:00	1	0	0
4	5	1/22/2020	Gansu	Mainland China	1/22/2020 17:00	0	0	0
...	...	...	...	...	...	...	...	...
306424	306425	5/29/2021	Zaporizhia Oblast	Ukraine	5/30/2021 4:20	102641	2335	95289
306425	306426	5/29/2021	Zeeland	Netherlands	5/30/2021 4:20	29147	245	0
306426	306427	5/29/2021	Zhejiang	Mainland China	5/30/2021 4:20	1364	1	1324
306427	306428	5/29/2021	Zhytomyr Oblast	Ukraine	5/30/2021 4:20	87550	1738	83790
306428	306429	5/29/2021	Zuid-Holland	Netherlands	5/30/2021 4:20	391559	4252	0

306429 rows × 8 columns

df.drop(['SNo','Last Update'],axis=1,inplace=True)

df.head(10)

	ObservationDate	Province/State	Country/Region	Confirmed	Deaths	Recovered
0	1/22/2020	Anhui	Mainland China	1	0	0
1	1/22/2020	Beijing	Mainland China	14	0	0
2	1/22/2020	Chongqing	Mainland China	6	0	0
3	1/22/2020	Fujian	Mainland China	1	0	0
4	1/22/2020	Gansu	Mainland China	0	0	0
5	1/22/2020	Guangdong	Mainland China	26	0	0
6	1/22/2020	Guangxi	Mainland China	2	0	0
7	1/22/2020	Guizhou	Mainland China	1	0	0
8	1/22/2020	Hainan	Mainland China	4	0	0
9	1/22/2020	Hebei	Mainland China	1	0	0

df.rename(columns={'ObservationDate':'Date','Province/State':'Province','Country/Region':'Country'},inplace=True)

df.head(10)

	Date	Province	Country	Confirmed	Deaths	Recovered
0	1/22/2020	Anhui	Mainland China	1	0	0
1	1/22/2020	Beijing	Mainland China	14	0	0
2	1/22/2020	Chongqing	Mainland China	6	0	0
3	1/22/2020	Fujian	Mainland China	1	0	0
4	1/22/2020	Gansu	Mainland China	0	0	0
5	1/22/2020	Guangdong	Mainland China	26	0	0
6	1/22/2020	Guangxi	Mainland China	2	0	0
7	1/22/2020	Guizhou	Mainland China	1	0	0
8	1/22/2020	Hainan	Mainland China	4	0	0
9	1/22/2020	Hebei	Mainland China	1	0	0

df['Date']=pd.to_datetime(df['Date'])

df.head(10)

	Date	Province	Country	Confirmed	Deaths	Recovered
0	2020-01-22	Anhui	Mainland China	1	0	0
1	2020-01-22	Beijing	Mainland China	14	0	0
2	2020-01-22	Chongqing	Mainland China	6	0	0
3	2020-01-22	Fujian	Mainland China	1	0	0
4	2020-01-22	Gansu	Mainland China	0	0	0
5	2020-01-22	Guangdong	Mainland China	26	0	0
6	2020-01-22	Guangxi	Mainland China	2	0	0
7	2020-01-22	Guizhou	Mainland China	1	0	0
8	2020-01-22	Hainan	Mainland China	4	0	0
9	2020-01-22	Hebei	Mainland China	1	0	0

df.describe()

	Confirmed	Deaths	Recovered
count	3.064290e+05	306429.000000	3.064290e+05
mean	8.567091e+04	2036.403268	5.042029e+04
std	2.775516e+05	6410.938048	2.015124e+05
min	-3.028440e+05	-178.000000	-8.544050e+05
25%	1.042000e+03	13.000000	1.100000e+01
50%	1.037500e+04	192.000000	1.751000e+03
75%	5.075200e+04	1322.000000	2.027000e+04
max	5.863138e+06	112385.000000	6.399531e+06

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 306429 entries, 0 to 306428
Data columns (total 6 columns):
 #   Column     Non-Null Count   Dtype         
---  ------     --------------   -----         
 0   Date       306429 non-null  datetime64[ns]
 1   Province   228329 non-null  object        
 2   Country    306429 non-null  object        
 3   Confirmed  306429 non-null  int64         
 4   Deaths     306429 non-null  int64         
 5   Recovered  306429 non-null  int64         
dtypes: datetime64[ns](1), int64(3), object(2)
memory usage: 14.0+ MB

df=df.fillna('NA')

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 306429 entries, 0 to 306428
Data columns (total 6 columns):
 #   Column     Non-Null Count   Dtype 
---  ------     --------------   ----- 
 0   Date       306429 non-null  object
 1   Province   306429 non-null  object
 2   Country    306429 non-null  object
 3   Confirmed  306429 non-null  int64 
 4   Deaths     306429 non-null  int64 
 5   Recovered  306429 non-null  int64 
dtypes: int64(3), object(3)
memory usage: 14.0+ MB

df2=df.groupby('Country')[['Country','Confirmed','Deaths','Recovered']].sum().reset_index()

df3=df2.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Recovered']].sum().reset_index()

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_1532/1467656081.py in <module>
----> 1 df3=df2.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Recovered']].sum().reset_index()

~\Anaconda3\lib\site-packages\pandas\core\frame.py in groupby(self, by, axis, level, as_index, sort, group_keys, squeeze, observed, dropna)
   7629         # error: Argument "squeeze" to "DataFrameGroupBy" has incompatible type
   7630         # "Union[bool, NoDefault]"; expected "bool"
-> 7631         return DataFrameGroupBy(
   7632             obj=self,
   7633             keys=by,

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in __init__(self, obj, keys, axis, level, grouper, exclusions, selection, as_index, sort, group_keys, squeeze, observed, mutated, dropna)
    887             from pandas.core.groupby.grouper import get_grouper
    888 
--> 889             grouper, exclusions, obj = get_grouper(
    890                 obj,
    891                 keys,

~\Anaconda3\lib\site-packages\pandas\core\groupby\grouper.py in get_grouper(obj, key, axis, level, sort, observed, mutated, validate, dropna)
    860                 in_axis, level, gpr = False, gpr, None
    861             else:
--> 862                 raise KeyError(gpr)
    863         elif isinstance(gpr, Grouper) and gpr.key is not None:
    864             # Add key to exclusions

KeyError: 'Date'

df2=df.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Recovered']].sum().reset_index()

df2

	Country	Date	Confirmed	Deaths	Recovered
0	Azerbaijan	2/28/2020	1	0	0
1	('St. Martin',)	3/10/2020	2	0	0
2	Afghanistan	1/1/2021	51526	2191	41727
3	Afghanistan	1/10/2021	53489	2277	43948
4	Afghanistan	1/11/2021	53538	2288	44137
...	...	...	...	...	...
87276	occupied Palestinian territory	3/12/2020	0	0	0
87277	occupied Palestinian territory	3/14/2020	0	0	0
87278	occupied Palestinian territory	3/15/2020	0	0	0
87279	occupied Palestinian territory	3/16/2020	0	0	0
87280	occupied Palestinian territory	3/17/2020	0	0	0

87281 rows × 5 columns

df2=df2[df2['Confirmed']>2000000]

df2

	Country	Date	Confirmed	Deaths	Recovered
3047	Argentina	2021-02-10	2001034	49674	1798120
3048	Argentina	2021-02-11	2008345	49874	1806260
3049	Argentina	2021-02-12	2015496	50029	1814160
3050	Argentina	2021-02-13	2021553	50188	1820965
3051	Argentina	2021-02-14	2025798	50236	1827118
...	...	...	...	...	...
83040	Ukraine	2021-05-25	2244084	51682	2028598
83041	Ukraine	2021-05-26	2247605	51898	2043720
83042	Ukraine	2021-05-27	2251242	52088	2060753
83043	Ukraine	2021-05-28	2254674	52252	2074174
83044	Ukraine	2021-05-29	2257904	52414	2084477

2621 rows × 5 columns

df2=df.groupby('Country')[['Country','Confirmed','Deaths','Recovered']].mean().reset_index()

df3=df2[df2['Deaths']>10000]

df3

	Country	Confirmed	Deaths	Recovered
8	Argentina	1.114355e+06	26738.280353	9.685437e+05
97	Indonesia	5.841102e+05	17115.262115	4.987140e+05
98	Iran	8.603214e+05	33786.281116	7.013155e+05
164	Poland	8.422142e+05	19804.592920	6.854766e+05
171	Romania	3.770867e+05	10079.753813	3.305183e+05
191	South Africa	7.670511e+05	22727.352550	6.874447e+05
212	Turkey	1.390879e+06	15373.388764	1.267799e+06

df2=df.groupby(['Date'])[['Date','Deaths']].mean().reset_index()

df2

	Date	Deaths
0	2020-01-22	0.425000
1	2020-01-23	0.708333
2	2020-01-24	0.604651
3	2020-01-25	0.913043
4	2020-01-26	1.142857
...	...	...
489	2021-05-25	4556.585621
490	2021-05-26	4573.260131
491	2021-05-27	4589.930719
492	2021-05-28	4605.381699
493	2021-05-29	4619.109804

494 rows × 2 columns

sorted_df = df2.sort_values(['Deaths'],ascending=False) 

sorted_df

	Date	Deaths
493	2021-05-29	4619.109804
492	2021-05-28	4605.381699
491	2021-05-27	4589.930719
490	2021-05-26	4573.260131
489	2021-05-25	4556.585621
...	...	...
4	2020-01-26	1.142857
3	2020-01-25	0.913043
1	2020-01-23	0.708333
2	2020-01-24	0.604651
0	2020-01-22	0.425000

494 rows × 2 columns

Matplotlib

import numpy as np
import matplotlib.pyplot as plt
x=np.linspace(0,10,1000)
plt.plot(x,np.sin(x))

[<matplotlib.lines.Line2D at 0x26f00ca0160>]

import numpy as np
import matplotlib.pyplot as plt
x=np.linspace(0,10,1000)
y=np.sin(x)
plt.plot(x,y)

[<matplotlib.lines.Line2D at 0x26f00da9580>]

plt.scatter(x,y)

<matplotlib.collections.PathCollection at 0x26f00e066d0>

plt.scatter(x[:30],y[:30])

<matplotlib.collections.PathCollection at 0x26f7d900fd0>

plt.scatter(x[::10],y[::10],color='red')

<matplotlib.collections.PathCollection at 0x26f00f17b80>

plt.scatter?

plt.plot(x,y,color='b')
plt.plot(x,np.cos(x),color='g')

[<matplotlib.lines.Line2D at 0x26f0234e7c0>]

Pandas & Matplotlib

import pandas as pd
import numpy as np
from sklearn.impute import SimpleImputer
df =pd.read_csv('D:\sayadur\Data Science\covid_19_data\covid_19_data.csv')

df

	SNo	ObservationDate	Province/State	Country/Region	Last Update	Confirmed	Deaths	Recovered
0	1	1/22/2020	Anhui	Mainland China	1/22/2020 17:00	1	0	0
1	2	1/22/2020	Beijing	Mainland China	1/22/2020 17:00	14	0	0
2	3	1/22/2020	Chongqing	Mainland China	1/22/2020 17:00	6	0	0
3	4	1/22/2020	Fujian	Mainland China	1/22/2020 17:00	1	0	0
4	5	1/22/2020	Gansu	Mainland China	1/22/2020 17:00	0	0	0
...	...	...	...	...	...	...	...	...
306424	306425	5/29/2021	Zaporizhia Oblast	Ukraine	5/30/2021 4:20	102641	2335	95289
306425	306426	5/29/2021	Zeeland	Netherlands	5/30/2021 4:20	29147	245	0
306426	306427	5/29/2021	Zhejiang	Mainland China	5/30/2021 4:20	1364	1	1324
306427	306428	5/29/2021	Zhytomyr Oblast	Ukraine	5/30/2021 4:20	87550	1738	83790
306428	306429	5/29/2021	Zuid-Holland	Netherlands	5/30/2021 4:20	391559	4252	0

306429 rows × 8 columns

df(10)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_1532/801129012.py in <module>
----> 1 df(10)

TypeError: 'DataFrame' object is not callable

df.head(10)

	Date	Province	Country	Confirmed	Deaths	Recovered
0	1/22/2020	Anhui	Mainland China	1	0	0
1	1/22/2020	Beijing	Mainland China	14	0	0
2	1/22/2020	Chongqing	Mainland China	6	0	0
3	1/22/2020	Fujian	Mainland China	1	0	0
4	1/22/2020	Gansu	Mainland China	0	0	0
5	1/22/2020	Guangdong	Mainland China	26	0	0
6	1/22/2020	Guangxi	Mainland China	2	0	0
7	1/22/2020	Guizhou	Mainland China	1	0	0
8	1/22/2020	Hainan	Mainland China	4	0	0
9	1/22/2020	Hebei	Mainland China	1	0	0

df.rename(columns={'ObservationDate':'Date','Province/State':'Province','Country/Region':'Country'},inplace=True)

df.drop(['SNo','Last Update'],axis=1,inplace=True)

countries=df2['country'].unique()
len(countries)

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
~\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
   3360             try:
-> 3361                 return self._engine.get_loc(casted_key)
   3362             except KeyError as err:

~\Anaconda3\lib\site-packages\pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

~\Anaconda3\lib\site-packages\pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'country'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_1532/378304976.py in <module>
----> 1 countries=df2['country'].unique()
      2 len(countries)

~\Anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
   3456             if self.columns.nlevels > 1:
   3457                 return self._getitem_multilevel(key)
-> 3458             indexer = self.columns.get_loc(key)
   3459             if is_integer(indexer):
   3460                 indexer = [indexer]

~\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
   3361                 return self._engine.get_loc(casted_key)
   3362             except KeyError as err:
-> 3363                 raise KeyError(key) from err
   3364 
   3365         if is_scalar(key) and isna(key) and not self.hasnans:

KeyError: 'country'

df2=df.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Rec

  File "C:\Users\sayadur\AppData\Local\Temp/ipykernel_1532/4197644617.py", line 1
    df2=df.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Rec
                                                                                  ^
SyntaxError: EOL while scanning string literal

df2=df.groupby('Country')[['Country','Confirmed','Deaths','Recovered']].sum().reset_index()

df2.head(10)

	Country	Confirmed	Deaths	Recovered
0	Azerbaijan	1	0	0
1	('St. Martin',)	2	0	0
2	Afghanistan	17026442	669075	13464399
3	Albania	19768869	375955	13945256
4	Algeria	27684358	834464	18959299
5	Andorra	2379802	32100	2162473
6	Angola	4764863	116489	3683041
7	Antigua and Barbuda	143868	4059	109958
8	Argentina	504802880	12112441	438750295
9	Armenia	42536277	770759	37101575

df3=df.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Recovered']].sum().reset_index()

df3.head(10)

	Country	Date	Confirmed	Deaths	Recovered
0	Azerbaijan	2/28/2020	1	0	0
1	('St. Martin',)	3/10/2020	2	0	0
2	Afghanistan	1/1/2021	51526	2191	41727
3	Afghanistan	1/10/2021	53489	2277	43948
4	Afghanistan	1/11/2021	53538	2288	44137
5	Afghanistan	1/12/2021	53584	2301	44608
6	Afghanistan	1/13/2021	53584	2301	44850
7	Afghanistan	1/14/2021	53775	2314	45298
8	Afghanistan	1/15/2021	53831	2324	45434
9	Afghanistan	1/16/2021	53938	2336	45465

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.impute import SimpleImputer
df =pd.read_csv('D:\sayadur\Data Science\covid_19_data\covid_19_data.csv')
df.rename(columns={'ObservationDate':'Date','Province/State':'Province','Country/Region':'Country'},inplace=True)
df['Date']=pd.to_datetime(df['Date'])
df.drop(['SNo','Last Update'],axis=1,inplace=True)
df3=df.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Recovered']].sum().reset_index()
df4=df.groupby(['Date'])[['Date','Confirmed','Deaths','Recovered']].sum().reset_index()
countries=df3['Country'].unique()
for idx in range(0,len(countries)):
    C=df3[df3['Country']==countries[idx]].reset_index()
    plt.scatter(np.arange(0,len(C)),C['Confirmed'],color='blue',label='Confirmed')
    plt.scatter(np.arange(0,len(C)),C['Recovered'],color='green',label='Recovered')
    plt.scatter(np.arange(0,len(C)),C['Deaths'],color='red',label='Deaths') 
    plt.title(countries[idx])
    plt.xlabel('Days since the first suspect')
    plt.ylabel('Number of case')
    plt.legend()
    plt.show()

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.impute import SimpleImputer
df =pd.read_csv('D:\sayadur\Data Science\covid_19_data\covid_19_data.csv')
df.rename(columns={'ObservationDate':'Date','Province/State':'Province','Country/Region':'Country'},inplace=True)
df['Date']=pd.to_datetime(df['Date'])
df.drop(['SNo','Last Update'],axis=1,inplace=True)
df4=df.groupby(['Date'])[['Date','Confirmed','Deaths','Recovered']].sum().reset_index()
C=df4
plt.scatter(np.arange(0,len(C)),C['Confirmed'],color='blue',label='Confirmed')
plt.scatter(np.arange(0,len(C)),C['Recovered'],color='green',label='Recovered')
plt.scatter(np.arange(0,len(C)),C['Deaths'],color='red',label='Deaths') 
plt.title('World')
plt.xlabel('Days since the first suspect')
plt.ylabel('Number of case')
plt.legend()
plt.show()
    

def countryCovidGraph():
    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.impute import SimpleImputer
    df =pd.read_csv('D:\sayadur\Data Science\covid_19_data\covid_19_data.csv')
    df.rename(columns={'ObservationDate':'Date','Province/State':'Province','Country/Region':'Country'},inplace=True)
    df['Date']=pd.to_datetime(df['Date'])
    df.drop(['SNo','Last Update'],axis=1,inplace=True)
    df3=df.groupby(['Country','Date'])[['Country','Date','Confirmed','Deaths','Recovered']].sum().reset_index()
    df4=df.groupby(['Date'])[['Date','Confirmed','Deaths','Recovered']].sum().reset_index()
    countries=df3['Country'].unique()
    for idx in range(0,len(countries)):
        C=df3[df3['Country']==countries[idx]].reset_index()
        plt.scatter(np.arange(0,len(C)),C['Confirmed'],color='blue',label='Confirmed')
        plt.scatter(np.arange(0,len(C)),C['Recovered'],color='green',label='Recovered')
        plt.scatter(np.arange(0,len(C)),C['Deaths'],color='red',label='Deaths') 
        plt.title(countries[idx])
        plt.xlabel('Days since the first suspect')
        plt.ylabel('Number of case')
        plt.legend()
        plt.show()
    return True 

countryCovidGraph()

True

pip install nbconvert[webpdf]

Requirement already satisfied: nbconvert[webpdf] in c:\users\sayadur\anaconda3\lib\site-packages (6.1.0)
Requirement already satisfied: entrypoints>=0.2.2 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (0.3)
Requirement already satisfied: pygments>=2.4.1 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (2.10.0)
Requirement already satisfied: mistune<2,>=0.8.1 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (0.8.4)
Requirement already satisfied: traitlets>=5.0 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (5.1.0)
Requirement already satisfied: nbformat>=4.4 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (5.1.3)
Requirement already satisfied: bleach in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (4.0.0)
Requirement already satisfied: testpath in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (0.5.0)
Requirement already satisfied: defusedxml in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (0.7.1)
Requirement already satisfied: jupyter-core in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (4.8.1)
Requirement already satisfied: jinja2>=2.4 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (2.11.3)
Requirement already satisfied: pandocfilters>=1.4.1 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (1.4.3)
Requirement already satisfied: jupyterlab-pygments in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (0.1.2)
Requirement already satisfied: nbclient<0.6.0,>=0.5.0 in c:\users\sayadur\anaconda3\lib\site-packages (from nbconvert[webpdf]) (0.5.3)
Collecting pyppeteer==0.2.2
  Downloading pyppeteer-0.2.2-py3-none-any.whl (145 kB)
Collecting pyee<8.0.0,>=7.0.1
  Downloading pyee-7.0.4-py2.py3-none-any.whl (12 kB)
Requirement already satisfied: appdirs<2.0.0,>=1.4.3 in c:\users\sayadur\anaconda3\lib\site-packages (from pyppeteer==0.2.2->nbconvert[webpdf]) (1.4.4)
Requirement already satisfied: urllib3<2.0.0,>=1.25.8 in c:\users\sayadur\anaconda3\lib\site-packages (from pyppeteer==0.2.2->nbconvert[webpdf]) (1.26.7)
Collecting websockets<9.0,>=8.1
  Downloading websockets-8.1.tar.gz (58 kB)
Requirement already satisfied: tqdm<5.0.0,>=4.42.1 in c:\users\sayadur\anaconda3\lib\site-packages (from pyppeteer==0.2.2->nbconvert[webpdf]) (4.62.3)
Requirement already satisfied: MarkupSafe>=0.23 in c:\users\sayadur\anaconda3\lib\site-packages (from jinja2>=2.4->nbconvert[webpdf]) (1.1.1)
Requirement already satisfied: jupyter-client>=6.1.5 in c:\users\sayadur\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert[webpdf]) (6.1.12)
Requirement already satisfied: async-generator in c:\users\sayadur\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert[webpdf]) (1.10)
Requirement already satisfied: nest-asyncio in c:\users\sayadur\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert[webpdf]) (1.5.1)
Requirement already satisfied: python-dateutil>=2.1 in c:\users\sayadur\anaconda3\lib\site-packages (from jupyter-client>=6.1.5->nbclient<0.6.0,>=0.5.0->nbconvert[webpdf]) (2.8.2)
Requirement already satisfied: tornado>=4.1 in c:\users\sayadur\anaconda3\lib\site-packages (from jupyter-client>=6.1.5->nbclient<0.6.0,>=0.5.0->nbconvert[webpdf]) (6.1)
Requirement already satisfied: pyzmq>=13 in c:\users\sayadur\anaconda3\lib\site-packages (from jupyter-client>=6.1.5->nbclient<0.6.0,>=0.5.0->nbconvert[webpdf]) (22.2.1)
Requirement already satisfied: pywin32>=1.0 in c:\users\sayadur\anaconda3\lib\site-packages (from jupyter-core->nbconvert[webpdf]) (228)
Requirement already satisfied: ipython-genutils in c:\users\sayadur\anaconda3\lib\site-packages (from nbformat>=4.4->nbconvert[webpdf]) (0.2.0)
Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in c:\users\sayadur\anaconda3\lib\site-packages (from nbformat>=4.4->nbconvert[webpdf]) (3.2.0)
Requirement already satisfied: pyrsistent>=0.14.0 in c:\users\sayadur\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.4->nbconvert[webpdf]) (0.18.0)
Requirement already satisfied: attrs>=17.4.0 in c:\users\sayadur\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.4->nbconvert[webpdf]) (21.2.0)
Requirement already satisfied: setuptools in c:\users\sayadur\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.4->nbconvert[webpdf]) (58.0.4)
Requirement already satisfied: six>=1.11.0 in c:\users\sayadur\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.4->nbconvert[webpdf]) (1.16.0)
Requirement already satisfied: colorama in c:\users\sayadur\anaconda3\lib\site-packages (from tqdm<5.0.0,>=4.42.1->pyppeteer==0.2.2->nbconvert[webpdf]) (0.4.4)
Requirement already satisfied: webencodings in c:\users\sayadur\anaconda3\lib\site-packages (from bleach->nbconvert[webpdf]) (0.5.1)
Requirement already satisfied: packaging in c:\users\sayadur\anaconda3\lib\site-packages (from bleach->nbconvert[webpdf]) (21.0)
Requirement already satisfied: pyparsing>=2.0.2 in c:\users\sayadur\anaconda3\lib\site-packages (from packaging->bleach->nbconvert[webpdf]) (3.0.4)
Building wheels for collected packages: websockets
  Building wheel for websockets (setup.py): started
  Building wheel for websockets (setup.py): finished with status 'done'
  Created wheel for websockets: filename=websockets-8.1-cp39-cp39-win_amd64.whl size=62758 sha256=020721ed39ecb589deec8a5cdfb2cef5ce9da54e530ba15376b3cd017eb58625
  Stored in directory: c:\users\sayadur\appdata\local\pip\cache\wheels\d8\b9\a0\b97b211aeda2ebd6ac2e43fc300d308dbf1f9df520ed390cae
Successfully built websockets
Installing collected packages: websockets, pyee, pyppeteer
Successfully installed pyee-7.0.4 pyppeteer-0.2.2 websockets-8.1
Note: you may need to restart the kernel to use updated packages.